Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    cognitive improvement memory reaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    us
    0.54
    er
    0.52
    0.51
    ie
    0.49
    ത്തക
    0.48
    en
    0.47
    rie
    0.46
    verb
    0.46
    rip
    0.46
    емо
    0.46
    POSITIVE LOGITS
    㥳
    0.54
    ")/
    0.48
    Всім
    0.48
     UIText
    0.46
     sain
    0.46
     trow
    0.46
     CARR
    0.45
    IRO
    0.44
    আই
    0.44
    ოში
    0.43
    Act Density 0.000%

    No Known Activations